tailwind
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data by reading and searching through project source code (TSX, JSX, and HTML files).
- Ingestion points: Reads files via Read, Grep, and Glob tools.
- Boundary markers: None present; the skill treats code content as data for pattern matching.
- Capability inventory: Uses Bash for searching and Edit for modifying files.
- Sanitization: None present. The skill uses specific regex patterns to target Tailwind classes, which limits the risk of executing embedded instructions within the code.
Audit Metadata